Share Email Print

Proceedings Paper

Melody retrieval on the web
Author(s): Wei Chai; Barry Vercoe
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This paper explores issues involved in a web-based query-by-humming system, which can find a piece of music in the digital music repository based on hummed melodies. Melody representation, melody matching, melody extraction and query construction are critical for an efficient and robust query-by-humming system and thus the focuses of this paper. Compared to previous systems, a new and more effective melody representation and corresponding melody matching methods which combined both pitch and rhythmic information were adopted, a whole set of tools and deliverable software were implemented, and experiments were conducted to evaluate the system. The experimental results demonstrate that our methods are more effective for most users than other existing methods.

Paper Details

Date Published: 10 December 2001
PDF: 16 pages
Proc. SPIE 4673, Multimedia Computing and Networking 2002, (10 December 2001); doi: 10.1117/12.449982
Show Author Affiliations
Wei Chai, MIT Media Lab. (United States)
Barry Vercoe, MIT Media Lab. (United States)

Published in SPIE Proceedings Vol. 4673:
Multimedia Computing and Networking 2002
Martin G. Kienzle; Prashant J. Shenoy, Editor(s)

© SPIE. Terms of Use
Back to Top